© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104165
    Prev
    Next
    INDEX
    Explanations

    you, you can, you win, you are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ꪹ
    -1.93
    i
    -1.88
    </em>
    -1.80
    ↵
    -1.70
    %，
    -1.67
     últimas
    -1.66
     own
    -1.63
     this
    -1.62
     milioni
    -1.62
    不会
    -1.58
    POSITIVE LOGITS
    {
    2.08
    (%)
    1.84
    strator
    1.82
    &.
    1.80
     وتم
    1.73
    ;?
    1.73
     tabPage
    1.72
    塤
    1.72
    
    1.71
     calificaciones
    1.70
    Activations Density 0.055%

    No Known Activations